UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Conditional Meta-Learning of Linear Representations

Denevi, G; Pontil, M; Ciliberto, C; (2021) Conditional Meta-Learning of Linear Representations. arXiv.org Green open access

[thumbnail of 2103.16277v1.pdf]
Preview
Text
2103.16277v1.pdf - Published Version

Download (902kB) | Preview

Abstract

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured by a single representation. In this work we overcome this issue by inferring a conditioning function, mapping the tasks' side information (such as the tasks' training dataset itself) into a representation tailored to the task at hand. We study environments in which our conditional strategy outperforms standard meta-learning, such as those in which tasks can be organized in separate clusters according to the representation they share. We then propose a meta-algorithm capable of leveraging this advantage in practice. In the unconditional setting, our method yields a new estimator enjoying faster learning rates and requiring less hyper-parameters to tune than current state-of-the-art methods. Our results are supported by preliminary experiments.

Type: Article
Title: Conditional Meta-Learning of Linear Representations
Open access status: An open access version is available from UCL Discovery
Publisher version: https://doi.org/10.48550/arXiv.2103.16277
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10125914
Downloads since deposit
7Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item